Saved in:
Bibliographic Details
Main Authors: Tong, Ziyi, Sun, Feifei, Nguyen, Le Minh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03121
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based membership inference attacks (MIAs) have become a widely adopted approach for assessing data exposure in large language models (LLMs), yet their effect in MLLMs remains unclear. We present the first comprehensive evaluation of extending these text-based MIA methods to multimodal settings. Our experiments under vision-and-text (V+T) and text-only (T-only) conditions across the DeepSeek-VL and InternVL model families show that in in-distribution settings, logit-based MIAs perform comparably across configurations, with a slight V+T advantage. Conversely, in out-of-distribution settings, visual inputs act as regularizers, effectively masking membership signals.